Skip to main content
Glama
Life Admin MCP

Life Admin MCP

by NKC27

Sort spending into a category

categorise

Assign bank transactions whose descriptions contain specified words to a category and optionally save a rule so future imports are sorted the same way.

Instructions

Put every transaction whose description contains these words (whole words, any case) into a category, and by default remember it so future imports are sorted the same way. Use after an import lists unsorted shops. Categories: bills (Bills & energy), groceries (Groceries), shopping (Shopping), going-out (Eating & going out), transport (Transport), tax (Tax), subscriptions (Subscriptions), savings (Savings), income (Income), transfers (Transfers), other (Other).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "match": "<match>",
      "category": "<category>"
    },
    "name": "categorise"
  }
}

Input Schema

NameRequiredDescriptionDefault
matchYesWords from the description, e.g. 'RED LION'
categoryYes
rememberNoSave as a rule for next time (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds meaningful behavior beyond annotations: the tool persists a rule by default so future imports are sorted the same way, which is the key side effect an agent must know before calling. Annotations only say readOnlyHint=false and non-idempotent; the description does not say whether a saved rule can later be undone or what happens when nothing matches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the action and matching rule, then the persistence default, then usage hint, then the category map. The category list is long but carries real information (slug-to-label mapping); little else is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description covers the important install-time knowledge: matching rules, default persistence, and valid categories. It is slightly incomplete on return behavior (how many transactions were categorised) and on reversing a remembered rule.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Explains matching semantics beyond the schema's example ('RED LION'): whole words, any case, substring of the transaction description. It also maps the raw enum slugs (bills, going-out, tax) to human-readable category labels, which the schema enum alone does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: put transactions whose description contains these words into a category, with the matching rule (whole words, any case) spelled out. It is clearly distinguishable from siblings like import_bank_file or update_item, which do not create categorisation rules.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete timing guidance - 'Use after an import lists unsorted shops' - which ties the tool to the import workflow. It does not name a sibling alternative or state when not to use it (e.g. correcting a single transaction versus bulk matching).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.